Hello Ben, Monday, December 11, 2006, 9:34:18 PM, you wrote:
BR> Robert Milkowski wrote: >> Hello eric, >> >> Saturday, December 9, 2006, 7:07:49 PM, you wrote: >> >> ek> Jim Mauro wrote: >> >>>>> Could be NFS synchronous semantics on file create (followed by >>>>> repeated flushing of the write cache). What kind of storage are you >>>>> using (feel free to send privately if you need to) - is it a thumper? >>>>> >>>> It's not clear why NFS-enforced synchronous semantics would induce >>>> different behavior than the same >>>> load to a local ZFS. >>>> >> >> ek> Actually i forgot he had 'zil_disable' turned on, so it won't matter in >> ek> this case. >> >> >> Ben, are you sure zil_disable was set to 1 BEFORE pool was imported? >> BR> Yes, absolutely. Set var in /etc/system, reboot, system come up. That BR> happened almost 2 months ago, long before this lock insanity problem BR> popped up. BR> To be clear, the ZIL issue was a problem for creation of a handful of BR> files of any size. Untar'ing a file was a massive performance drain. BR> This issue, other the other hand, deals with thousands of little files BR> being created all the time (IMAP Locks). These are separate issues from BR> my point of view. With ZIL slowness NFS performance was just slow but BR> we didn't see massive CPU usage, with this issue on the other hand we BR> were seeing waves in 10 second-ish cycles where the run queue would go BR> sky high with 0 idle. Please see the earlier mails for examples of the BR> symptoms. Ok. And just another question - is nfs file system mounted with noac options on imap server and application is doing chdir() to nfs directories? I'm not sure if it's fixed - if not your nfs client on every chdir() will generate lot of small traffic to nfs server starving it of cpu. -- Best regards, Robert mailto:[EMAIL PROTECTED] http://milek.blogspot.com _______________________________________________ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
